feat: orchestration harness, selective install, observer improvements

.agents/skills/claude-api/SKILL.md

@@ -230,6 +230,8 @@ print(f"Cache creation: {message.usage.cache_creation_input_tokens}")
 Process large volumes asynchronously at 50% cost reduction:
 
 ```python
+import time
+
 batch = client.messages.batches.create(
     requests=[
         {
@@ -306,6 +308,8 @@ while True:
 ## Error Handling
 
 ```python
+import time
+
 from anthropic import APIError, RateLimitError, APIConnectionError
 
 try:

.agents/skills/crosspost/SKILL.md

@@ -148,6 +148,7 @@ A pattern I've been using that's made a real difference:
 If using a crossposting service (e.g., Postbridge, Buffer, or a custom API), the pattern looks like:
 
 ```python
+import os
 import requests
 
 resp = requests.post(

.agents/skills/x-api/SKILL.md

@@ -92,6 +92,7 @@ def post_thread(oauth, tweets: list[str]) -> list[str]:
         if reply_to:
             payload["reply"] = {"in_reply_to_tweet_id": reply_to}
         resp = oauth.post("https://api.x.com/2/tweets", json=payload)
+        resp.raise_for_status()
         tweet_id = resp.json()["data"]["id"]
         ids.append(tweet_id)
         reply_to = tweet_id
@@ -167,6 +168,8 @@ resp = oauth.post(
 Always check `x-rate-limit-remaining` and `x-rate-limit-reset` headers.
 
 ```python
+import time
+
 remaining = int(resp.headers.get("x-rate-limit-remaining", 0))
 if remaining < 5:
     reset = int(resp.headers.get("x-rate-limit-reset", 0))